WhisperFix – Chinese ASR post-editor

Make Whisper's Chinese transcription accurate enough to actually use

Problem

A V2EX user reports Whisper-large-v3-turbo works well in English but Chinese output has errors in almost every sentence, hurting meeting notes and podcast transcription. Switching models is costly, and many users need local deployment.

Solution

A local-first post-processing tool that uses lightweight Chinese correction models or rule engines to fix Whisper output, restore punctuation, and optimize segmentation. Supports batch audio processing and can be embedded as an API.

Users

Developers, podcasters, and meeting note-takers needing Chinese transcription, especially those requiring privacy and local deployment

MVP

Import Whisper output with timestamps; automatic Chinese correction and punctuation restoration; simple batch UI or CLI; export to SRT/VTT; API for integration

Revenue

One-time purchase for local tool; usage-based cloud API; enterprise tier with custom glossary and private deployment

Why now

Chinese ASR demand is high but Whisper's Chinese is weak; open Chinese correction models are maturing, enabling indie devs to build a cost-effective post-processor